Direct low-field MRI super-resolution using undersampled k-space

⋅

arXiv:2603.00668v1 Announce Type: new Abstract: Low-field magnetic resonance imaging (MRI) provides affordable access to diagnostic imaging but suffers from prolonged acquisition and limited image quality. Accelerated imaging can be achieved with k-space undersampling, while super-resolution (SR) and image quality transfer (IQT) methods typically rely on spatial-domain post-processing. In this work, we propose a novel framework for reconstructing high-field MR like images directly from undersampled low-field k-space. Our approach employs a k-space dual channel U-Net that processes the real […]

Ver mais

Liked Liked

LooC: Effective Low-Dimensional Codebook for Compositional Vector Quantization

⋅

arXiv:2601.00222v1 Announce Type: new Abstract: Vector quantization (VQ) is a prevalent and fundamental technique that discretizes continuous feature vectors by approximating them using a codebook. As the diversity and complexity of data and models continue to increase, there is an urgent need for high-capacity, yet more compact VQ methods. This paper aims to reconcile this conflict by presenting a new approach called LooC, which utilizes an effective Low-dimensional codebook for Compositional vector quantization. Firstly, LooC introduces a parameter-efficient […]

Ver mais

Liked Liked

Rev. Dr. Richard Turnbull: Scholar, Teacher, Friend

⋅

The Rev. Dr. Richard Turnbull, long-time friend of the Acton Institute, sadly died on November 26, not long after being diagnosed with terminal cancer. Many friends, colleagues, and collaborators joined a Whatsapp group to pray for Richard and his family in his final weeks, and the affection and admiration that so many people had for him was clearly expressed over those weeks. Continue Reading…

Ver mais

Liked Liked

Active Multiple-Prediction-Powered Inference

⋅

arXiv:2605.08429v1 Announce Type: new Abstract: Post-deployment monitoring of healthcare AI requires statistically valid, label-efficient methods, but gold-standard labels from clinician chart review are expensive. Prediction-powered inference (PPI) and active statistical inference (ASI) reduce label cost by combining a small labeled sample with abundant model predictions, but both are restricted to a single predictor, a poor fit for modern clinical pipelines that have multiple predictors of differing cost and accuracy available at inference time. We propose Active Multiple-Prediction-Powered Inference […]

Ver mais

Liked Liked

FedVG: Gradient-Guided Aggregation for Enhanced Federated Learning

⋅

Federated Learning (FL) enables collaborative model training across multiple clients without sharing their private data. However, data heterogeneity across clients leads to client drift, which degrades the overall generalization performance of the model. This effect is further compounded by overemphasis on poorly performing clients. To address this problem, we propose FedVG, a novel gradient-based federated aggregation framework that leverages a global validation set to guide the optimization process. Such a global validation set can be established using readily […]

Ver mais

Liked Liked

Graph-GRPO: Training Graph Flow Models with Reinforcement Learning

⋅

Graph generation is a fundamental task with broad applications, such as drug discovery. Recently, discrete flow matching-based graph generation, aka, graph flow model (GFM), has emerged due to its superior performance and flexible sampling. However, effectively aligning GFMs with complex human preferences or task-specific objectives remains a significant challenge. In this paper, we propose Graph-GRPO, an online reinforcement learning (RL) framework for training GFMs under verifiable rewards. Our method makes two key contributions: (1) We derive an analytical […]

Ver mais

Liked Liked

Amortising Inference and Meta-Learning Priors in Neural Networks

⋅

arXiv:2602.08782v1 Announce Type: new Abstract: One of the core facets of Bayesianism is in the updating of prior beliefs in light of new evidence$text{ — }$so how can we maintain a Bayesian approach if we have no prior beliefs in the first place? This is one of the central challenges in the field of Bayesian deep learning, where it is not clear how to represent beliefs about a prediction task by prior distributions over model parameters. Bridging the […]

Ver mais

Liked Liked

The State of AI Translation in 2026: iFlytek Real-Time Translation Earbuds

⋅

There are a lot of translation tools available today, and most of them are free. Open your phone, launch Google Translate, and you already have a perfectly functional solution in your pocket. That’s why devices like the iFlytek AI translation earbuds fall into a category I’m very familiar with reviewing: luxury tech. Luxury tech is not about necessity. It’s about experience. Nobody needs a VR headset, an AR headset, or premium peripherals for niche use cases. But for […]

Ver mais

Liked Liked

Load More

↑

Digitado © 2026